Skip to main content
Back to challenges
Challenge

Multi-Omics ALS Biomarker Longitudinal Fusion Pipeline with Pydantic AI

NIH news highlights blood-based biomarker breakthroughs for predicting pre-symptomatic ALS symptom emergence. In this challenge, participants will build a multi-omics longitudinal data integration pipeline using Pydantic AI. The agent will ingest serum proteomics data (NfL, pNfH), transcriptomic panels, and clinical histories to predict disease conversion timelines with strict schema-enforced output constraints.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build a type-safe multi-omics ALS biomarker longitudinal prediction pipeline using Pydantic AI.

Delivery guide

How work is evaluated

Evaluation

Evaluates hazard ratio estimation precision and time-to-conversion prediction.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

check_valid_hazard_ratio

Ensure hazard ratio is positive float

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

hazard_ratio_mae

Mean Absolute Error of estimated hazard ratio against longitudinal survival ground truth • target: 0.25 • range: 0-5

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Construct Pydantic AI agents for multi-modal omics longitudinal integration

  • Ingest plasma proteomics (NfL) and RNA expression panels

  • Apply time-to-event survival models (Cox PH, Random Survival Forests) via Python dependencies

  • Enforce strictly validated patient conversion prognosis schemas

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic multi-omics panels (plasma NfL, pNfH, miRNA expression) paired with conversion timeline outcomes.

Challenge setup

Evaluates hazard ratio estimation precision and time-to-conversion prediction.

Challenge input

JSON containing nfl_pg_ml, pnfh_pg_ml, mirna_133b_expr

Pydantic AI

Mandatory Pydantic AI framework

Evaluated output

JSON containing hazard_ratio (float), predicted_conversion_window_months (string)

Evaluation checks
  • Ensure hazard ratio is positive float
  • Mean Absolute Error of estimated hazard ratio against longitudinal survival ground truth • target: 0.25 • r...
Configured evaluation evidence
  • Benchmark: OmicsSurvival-Bench
  • Hazard Ratio Mae target: 0.25
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Pydantic AI · Required
  • Merge · Optional
  • Llama 3.2 · Optional
Orchestration
  • Pydantic AI · Required

Evaluation contract

  • check_valid_hazard_ratio · Weight 1
  • hazard_ratio_mae · Weight 1

Metrics

  • hazard_ratio_mae · Target 0.25

Benchmarks

  • OmicsSurvival-Bench
  • biotech

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing nfl_pg_ml, pnfh_pg_ml, mirna_133b_expr

    Output: JSON containing hazard_ratio (float), predicted_conversion_window_months (string)

    Execution harness: Python

Evaluation tools

  • Pydantic AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Multi-Omics ALS Biomarker Longitudinal Fusion Pipeline with Pydantic AI